Index

A

address (web2vec.extractors.whois_features.WhoisFeatures attribute) api_timeout (web2vec.config.Config attribute)

ASN (web2vec.extractors.url_geo_features.GeoLiteDbType attribute) asn (web2vec.extractors.url_geo_features.URLGeoFeatures attribute) average_subdomain_length (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute)

B

body_length (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) (web2vec.extractors.http_response_features.HttpResponseFeatures attribute) body_length() (in module web2vec.extractors.html_body_features) (in module web2vec.extractors.http_response_features) body_to_special_char_ratio (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) (web2vec.extractors.http_response_features.HttpResponseFeatures attribute)

body_to_special_char_ratio() (in module web2vec.extractors.html_body_features) (in module web2vec.extractors.http_response_features) BounceRate (web2vec.extractors.external_api.similar_web_features.Engagements attribute) brave_search_api_key (web2vec.config.Config attribute) build_graph() (in module web2vec.extractors.network_features)

C

Category (web2vec.extractors.external_api.similar_web_features.SimilarWebFeatures attribute) CategoryRank (web2vec.extractors.external_api.similar_web_features.SimilarWebFeatures attribute) CertificateExtractor (class in web2vec.crawlers.extractors) CertificateFeatures (class in web2vec.extractors.ssl_certification_features) check_forms() (in module web2vec.extractors.http_response_features) check_header_content_security_policy() (in module web2vec.extractors.http_response_features) check_header_strict_transport_security() (in module web2vec.extractors.http_response_features) check_header_x_content_type_options() (in module web2vec.extractors.http_response_features) check_header_x_frame_options() (in module web2vec.extractors.http_response_features) check_header_x_xss_protection() (in module web2vec.extractors.http_response_features) check_https() (in module web2vec.extractors.http_response_features) check_obfuscated_scripts() (in module web2vec.extractors.html_body_features) (in module web2vec.extractors.http_response_features) check_phish_phishtank() (in module web2vec.extractors.external_api.phish_tank_features) check_redirects() (in module web2vec.extractors.http_response_features) check_server_version() (in module web2vec.extractors.http_response_features) check_ssl() (in module web2vec.extractors.ssl_certification_features) check_suspicious_keywords() (in module web2vec.extractors.html_body_features) (in module web2vec.extractors.http_response_features) city (web2vec.extractors.whois_features.WhoisFeatures attribute) compute_derived_features() (web2vec.extractors.dns_features.DNSFeatures method) Config (class in web2vec.config) contains_forms (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) (web2vec.extractors.http_response_features.HttpResponseFeatures attribute) contains_keywords() (in module web2vec.extractors.url_lexical_features) contains_obfuscated_scripts (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) (web2vec.extractors.http_response_features.HttpResponseFeatures attribute) contains_suspicious_keywords (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) (web2vec.extractors.http_response_features.HttpResponseFeatures attribute) copyright (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) count_ampersand_directory (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_ampersand_domain (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_ampersand_parameters (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_ampersand_url (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_asterisk_directory (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_asterisk_domain (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_asterisk_parameters (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_asterisk_url (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_at_directory (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_at_domain (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_at_parameters (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_at_url (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_char() (in module web2vec.extractors.url_lexical_features) count_comma_directory (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_comma_domain (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_comma_parameters (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_comma_url (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_dash_directory (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_dash_domain (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_dash_parameters (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_dash_url (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_dollar_directory (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_dollar_domain (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_dollar_parameters (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_dollar_url (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_dot_directory (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_dot_domain (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_dot_parameters (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_dot_url (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute)

count_equals_directory (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_equals_domain (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_equals_parameters (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_equals_url (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_exclamation_directory (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_exclamation_domain (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_exclamation_parameters (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_exclamation_url (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_hash_directory (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_hash_domain (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_hash_parameters (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_hash_url (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_ips (web2vec.extractors.dns_features.DNSFeatures property) count_mx_servers (web2vec.extractors.dns_features.DNSFeatures property) count_name_servers (web2vec.extractors.dns_features.DNSFeatures property) count_percent_directory (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_percent_domain (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_percent_parameters (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_percent_url (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_plus_directory (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_plus_domain (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_plus_parameters (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_plus_url (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_question_directory (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_question_domain (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_question_parameters (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_question_url (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_redirects() (in module web2vec.extractors.http_response_features) count_slash_directory (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_slash_domain (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_slash_parameters (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_slash_url (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_space_directory (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_space_domain (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_space_parameters (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_space_url (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_tilde_directory (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_tilde_domain (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_tilde_parameters (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_tilde_url (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_underscore_directory (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_underscore_domain (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_underscore_parameters (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_underscore_url (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) count_vowels() (in module web2vec.extractors.url_lexical_features) Country (web2vec.extractors.external_api.similar_web_features.TopCountryShare attribute) COUNTRY (web2vec.extractors.url_geo_features.GeoLiteDbType attribute) country (web2vec.extractors.whois_features.WhoisFeatures attribute) country_code (web2vec.extractors.url_geo_features.URLGeoFeatures attribute) CountryCode (web2vec.extractors.external_api.similar_web_features.SimilarWebFeatures attribute) (web2vec.extractors.external_api.similar_web_features.TopCountryShare attribute) CountryRank (web2vec.extractors.external_api.similar_web_features.SimilarWebFeatures attribute) Cpc (web2vec.extractors.external_api.similar_web_features.TopKeyword attribute) crawler_output_path (web2vec.config.Config attribute) crawler_spider_depth_limit (web2vec.config.Config attribute) create_directories() (in module web2vec.utils) created_within_30_days (web2vec.extractors.whois_features.WhoisFeatures attribute) created_within_365_days (web2vec.extractors.whois_features.WhoisFeatures attribute) creation_date (web2vec.extractors.whois_features.WhoisFeatures attribute) creation_datetime (web2vec.extractors.whois_features.WhoisFeatures attribute)

D

date (web2vec.extractors.external_api.similar_web_features.EstimatedMonthlyVisit attribute) date_added (web2vec.extractors.external_api.url_haus_features.URLHausFeatures attribute) days_until_expiration (web2vec.extractors.ssl_certification_features.CertificateFeatures attribute) (web2vec.extractors.whois_features.WhoisFeatures attribute) default_output_path (web2vec.config.Config attribute) Description (web2vec.extractors.external_api.similar_web_features.SimilarWebFeatures attribute) detect_api_endpoints() (in module web2vec.extractors.html_body_features) detect_likely_js_spa() (in module web2vec.extractors.html_body_features) Direct (web2vec.extractors.external_api.similar_web_features.TrafficSource attribute) directory_length (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) DNSExtractor (class in web2vec.crawlers.extractors) DNSFeatures (class in web2vec.extractors.dns_features) DNSRecordFeatures (class in web2vec.extractors.dns_features)

dnssec (web2vec.extractors.whois_features.WhoisFeatures attribute) domain (web2vec.extractors.dns_features.DNSFeatures attribute) (web2vec.extractors.external_api.open_pagerank_features.OpenPageRankFeatures attribute) (web2vec.extractors.external_api.phish_tank_features.PhishTankFeatures property) (web2vec.extractors.external_api.url_haus_features.URLHausFeatures property) domain_age (web2vec.extractors.whois_features.WhoisFeatures property) domain_age_days (web2vec.extractors.whois_features.WhoisFeatures attribute) domain_contains_keywords (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) domain_entropy (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) domain_google_index (web2vec.extractors.external_api.google_index_features.GoogleIndexFeatures attribute) domain_in_ip_format (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) domain_length (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) domain_name (web2vec.extractors.whois_features.WhoisFeatures attribute) domain_spf (web2vec.extractors.dns_features.DNSFeatures attribute)

E

email_present_in_url (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) emails (web2vec.extractors.whois_features.WhoisFeatures attribute) Engagements (class in web2vec.extractors.external_api.similar_web_features) (web2vec.extractors.external_api.similar_web_features.SimilarWebFeatures attribute) entropy() (in module web2vec.utils) entropy_of_url (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) EstimatedMonthlyVisit (class in web2vec.extractors.external_api.similar_web_features) EstimatedMonthlyVisits (web2vec.extractors.external_api.similar_web_features.SimilarWebFeatures attribute) EstimatedValue (web2vec.extractors.external_api.similar_web_features.TopKeyword attribute) expiration_date (web2vec.extractors.whois_features.WhoisFeatures attribute) expiration_datetime (web2vec.extractors.whois_features.WhoisFeatures attribute) expires_within_30_days (web2vec.extractors.ssl_certification_features.CertificateFeatures attribute) (web2vec.extractors.whois_features.WhoisFeatures attribute) expires_within_7_days (web2vec.extractors.ssl_certification_features.CertificateFeatures attribute) (web2vec.extractors.whois_features.WhoisFeatures attribute)

extract_features() (web2vec.crawlers.extractors.CertificateExtractor method) (web2vec.crawlers.extractors.DNSExtractor method) (web2vec.crawlers.extractors.Extractor method) (web2vec.crawlers.extractors.GoogleIndexExtractor method) (web2vec.crawlers.extractors.HtmlBodyExtractor method) (web2vec.crawlers.extractors.HttpResponseExtractor method) (web2vec.crawlers.extractors.OpenPageRankExtractor method) (web2vec.crawlers.extractors.OpenPhishExtractor method) (web2vec.crawlers.extractors.PhishTankExtractor method) (web2vec.crawlers.extractors.SimilarWebExtractor method) (web2vec.crawlers.extractors.UrlGeoExtractor method) (web2vec.crawlers.extractors.UrlHausExtractor method) (web2vec.crawlers.extractors.UrlLexicalExtractor method) (web2vec.crawlers.extractors.WhoisExtractor method) extract_ttl (web2vec.extractors.dns_features.DNSFeatures property) Extractor (class in web2vec.crawlers.extractors)

F

favicon_url (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) FEATURE_CLASS (web2vec.crawlers.extractors.CertificateExtractor attribute) (web2vec.crawlers.extractors.DNSExtractor attribute) (web2vec.crawlers.extractors.Extractor attribute) (web2vec.crawlers.extractors.GoogleIndexExtractor attribute) (web2vec.crawlers.extractors.HtmlBodyExtractor attribute) (web2vec.crawlers.extractors.HttpResponseExtractor attribute) (web2vec.crawlers.extractors.OpenPageRankExtractor attribute) (web2vec.crawlers.extractors.OpenPhishExtractor attribute) (web2vec.crawlers.extractors.PhishTankExtractor attribute) (web2vec.crawlers.extractors.SimilarWebExtractor attribute) (web2vec.crawlers.extractors.UrlGeoExtractor attribute) (web2vec.crawlers.extractors.UrlHausExtractor attribute) (web2vec.crawlers.extractors.UrlLexicalExtractor attribute) (web2vec.crawlers.extractors.WhoisExtractor attribute) FEATURE_TYPE (web2vec.crawlers.extractors.CertificateExtractor attribute) (web2vec.crawlers.extractors.DNSExtractor attribute) (web2vec.crawlers.extractors.Extractor attribute) (web2vec.crawlers.extractors.GoogleIndexExtractor attribute) (web2vec.crawlers.extractors.HtmlBodyExtractor attribute) (web2vec.crawlers.extractors.HttpResponseExtractor attribute) (web2vec.crawlers.extractors.OpenPageRankExtractor attribute) (web2vec.crawlers.extractors.OpenPhishExtractor attribute) (web2vec.crawlers.extractors.PhishTankExtractor attribute) (web2vec.crawlers.extractors.SimilarWebExtractor attribute) (web2vec.crawlers.extractors.UrlGeoExtractor attribute) (web2vec.crawlers.extractors.UrlHausExtractor attribute) (web2vec.crawlers.extractors.UrlLexicalExtractor attribute) (web2vec.crawlers.extractors.WhoisExtractor attribute)

features_name() (web2vec.crawlers.extractors.Extractor method) fetch_file_from_url() (in module web2vec.utils) fetch_file_from_url_and_read() (in module web2vec.utils) fetch_url() (in module web2vec.utils) find_copyright() (in module web2vec.extractors.html_body_features) find_favicon() (in module web2vec.extractors.html_body_features) find_logo() (in module web2vec.extractors.html_body_features) found_anchors (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) found_api_endpoints (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) found_forms (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) found_images (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) found_media (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) found_network_requests (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute)

G

GeoLiteDbType (class in web2vec.extractors.url_geo_features) get_asn() (in module web2vec.extractors.url_geo_features) get_certificate_features() (in module web2vec.extractors.ssl_certification_features) get_certificate_features_cached() (in module web2vec.extractors.ssl_certification_features) get_country() (in module web2vec.extractors.url_geo_features) get_dns_features() (in module web2vec.extractors.dns_features) get_dns_features_cached() (in module web2vec.extractors.dns_features) get_domain_from_url() (in module web2vec.utils) get_file_path_for_url() (in module web2vec.utils) get_geolite_db_files() (in module web2vec.extractors.url_geo_features) get_github_repo_release_info() (in module web2vec.utils) get_google_index_features() (in module web2vec.extractors.external_api.google_index_features) get_google_index_features_cached() (in module web2vec.extractors.external_api.google_index_features) get_html_body_features() (in module web2vec.extractors.html_body_features) get_http_response_features() (in module web2vec.extractors.http_response_features) get_ip_from_domain() (in module web2vec.utils) get_ip_from_url() (in module web2vec.utils) get_open_page_rank_features() (in module web2vec.extractors.external_api.open_pagerank_features) (web2vec.extractors.external_api.open_pagerank_features.OpenPageRankAPI method) get_open_page_rank_features_cached() (in module web2vec.extractors.external_api.open_pagerank_features)

get_open_phish_features() (in module web2vec.extractors.external_api.open_phish_features) get_open_phish_features_cached() (in module web2vec.extractors.external_api.open_phish_features) get_phishtank_features() (in module web2vec.extractors.external_api.phish_tank_features) get_phishtank_features_cached() (in module web2vec.extractors.external_api.phish_tank_features) get_phishtank_feed() (in module web2vec.extractors.external_api.phish_tank_features) get_similar_web_features() (in module web2vec.extractors.external_api.similar_web_features) get_similar_web_features_cached() (in module web2vec.extractors.external_api.similar_web_features) get_title() (web2vec.crawlers.models.WebPage method) get_tls_certificate() (in module web2vec.extractors.ssl_certification_features) get_url_geo_features() (in module web2vec.extractors.url_geo_features) get_url_geo_features_cached() (in module web2vec.extractors.url_geo_features) get_url_haus_features() (in module web2vec.extractors.external_api.url_haus_features) get_url_haus_features_cached() (in module web2vec.extractors.external_api.url_haus_features) get_url_lexical_features() (in module web2vec.extractors.url_lexical_features) get_url_lexical_features_cached() (in module web2vec.extractors.url_lexical_features) get_whois_features() (in module web2vec.extractors.whois_features) get_whois_features_cached() (in module web2vec.extractors.whois_features) GlobalRank (web2vec.extractors.external_api.similar_web_features.SimilarWebFeatures attribute) GoogleIndexExtractor (class in web2vec.crawlers.extractors) GoogleIndexFeatures (class in web2vec.extractors.external_api.google_index_features)

H

has_repeated_digits() (in module web2vec.extractors.url_lexical_features) having_anchor (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) having_digit_in_subdomain (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) having_fragment (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) having_hyphen_in_subdomain (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) having_special_char_in_subdomain (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute)

having_underscore_in_subdomain (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) hidden_elements() (in module web2vec.extractors.html_body_features) html_snapshot_path (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) HtmlBodyExtractor (class in web2vec.crawlers.extractors) HtmlBodyFeatures (class in web2vec.extractors.html_body_features) HttpResponseExtractor (class in web2vec.crawlers.extractors) HttpResponseFeatures (class in web2vec.extractors.http_response_features)

I

id (web2vec.extractors.external_api.url_haus_features.URLHausFeatures attribute) iframe_redirection (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) iframe_redirection() (in module web2vec.extractors.html_body_features) is_certificate_trusted() (in module web2vec.extractors.ssl_certification_features) is_certificate_valid() (in module web2vec.extractors.ssl_certification_features) is_expired (web2vec.extractors.ssl_certification_features.CertificateFeatures attribute) (web2vec.extractors.whois_features.WhoisFeatures attribute) is_external_url() (in module web2vec.extractors.html_body_features) is_indexed (web2vec.extractors.external_api.google_index_features.GoogleIndexFeatures attribute) is_ip (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute)

is_live (web2vec.extractors.http_response_features.HttpResponseFeatures attribute) is_live() (in module web2vec.extractors.http_response_features) is_numerical_type() (in module web2vec.utils) is_phishing (web2vec.extractors.external_api.open_phish_features.OpenPhishFeatures attribute) is_trusted (web2vec.extractors.ssl_certification_features.CertificateFeatures attribute) is_valid (web2vec.extractors.ssl_certification_features.CertificateFeatures attribute) issuer (web2vec.extractors.ssl_certification_features.CertificateFeatures attribute) issuer_common_name (web2vec.extractors.ssl_certification_features.CertificateFeatures attribute) issuer_is_free_ca (web2vec.extractors.ssl_certification_features.CertificateFeatures attribute) issuer_is_lets_encrypt (web2vec.extractors.ssl_certification_features.CertificateFeatures attribute) issuer_organization_name (web2vec.extractors.ssl_certification_features.CertificateFeatures attribute)

L

LargeScreenshot (web2vec.extractors.external_api.similar_web_features.SimilarWebFeatures attribute) last_online (web2vec.extractors.external_api.url_haus_features.URLHausFeatures attribute)

likely_js_spa (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) logo_url (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute)

M

Mail (web2vec.extractors.external_api.similar_web_features.TrafficSource attribute) min_ttl (web2vec.extractors.dns_features.DNSFeatures attribute) missing_content_security_policy (web2vec.extractors.http_response_features.HttpResponseFeatures attribute) missing_strict_transport_security (web2vec.extractors.http_response_features.HttpResponseFeatures attribute) missing_x_content_type_options (web2vec.extractors.http_response_features.HttpResponseFeatures attribute) missing_x_frame_options (web2vec.extractors.http_response_features.HttpResponseFeatures attribute) missing_x_xss_protection (web2vec.extractors.http_response_features.HttpResponseFeatures attribute) model_config (web2vec.config.Config attribute) module web2vec web2vec.config web2vec.crawlers web2vec.crawlers.extractors web2vec.crawlers.models web2vec.crawlers.spiders web2vec.extractors web2vec.extractors.dns_features web2vec.extractors.external_api web2vec.extractors.external_api.google_index_features web2vec.extractors.external_api.open_pagerank_features web2vec.extractors.external_api.open_phish_features web2vec.extractors.external_api.phish_tank_features web2vec.extractors.external_api.similar_web_features web2vec.extractors.external_api.url_haus_features web2vec.extractors.html_body_features web2vec.extractors.http_response_features web2vec.extractors.network_features web2vec.extractors.ssl_certification_features web2vec.extractors.url_geo_features web2vec.extractors.url_lexical_features web2vec.extractors.whois_features web2vec.utils web2vec.version

Month (web2vec.extractors.external_api.similar_web_features.Engagements attribute) mouse_over_effect (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) mouse_over_effect() (in module web2vec.extractors.html_body_features)

N

name (web2vec.crawlers.spiders.Web2VecSpider attribute) Name (web2vec.extractors.external_api.similar_web_features.TopKeyword attribute) name (web2vec.extractors.whois_features.WhoisFeatures attribute) name_servers (web2vec.extractors.whois_features.WhoisFeatures attribute) not_after (web2vec.extractors.ssl_certification_features.CertificateFeatures attribute) not_before (web2vec.extractors.ssl_certification_features.CertificateFeatures attribute) num_api_endpoints (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) num_email_forms (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) num_email_forms() (in module web2vec.extractors.html_body_features) num_external_iframes (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) num_external_iframes() (in module web2vec.extractors.html_body_features) num_external_network_requests (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) num_external_scripts (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) num_external_scripts() (in module web2vec.extractors.html_body_features) num_external_styles (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) num_external_styles() (in module web2vec.extractors.html_body_features) num_forms (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) num_forms() (in module web2vec.extractors.html_body_features) num_forms_external_action (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) num_forms_external_action() (in module web2vec.extractors.html_body_features) num_forms_get (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) num_forms_get() (in module web2vec.extractors.html_body_features) num_forms_post (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) num_forms_post() (in module web2vec.extractors.html_body_features) num_hidden_elements (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) num_iframes_http (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) num_iframes_http() (in module web2vec.extractors.html_body_features) num_images (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) (web2vec.extractors.http_response_features.HttpResponseFeatures attribute)

num_images() (in module web2vec.extractors.html_body_features) (in module web2vec.extractors.http_response_features) num_internal_links (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) num_internal_links() (in module web2vec.extractors.html_body_features) num_links (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) (web2vec.extractors.http_response_features.HttpResponseFeatures attribute) num_links() (in module web2vec.extractors.html_body_features) (in module web2vec.extractors.http_response_features) num_media_external (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) num_media_external() (in module web2vec.extractors.html_body_features) num_media_http (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) num_media_http() (in module web2vec.extractors.html_body_features) num_meta_tags (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) num_meta_tags() (in module web2vec.extractors.html_body_features) num_network_requests (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) num_safe_anchors (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) num_safe_anchors() (in module web2vec.extractors.html_body_features) num_scripts_http (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) num_scripts_http() (in module web2vec.extractors.html_body_features) num_styles_http (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) num_styles_http() (in module web2vec.extractors.html_body_features) num_titles (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) (web2vec.extractors.http_response_features.HttpResponseFeatures attribute) num_titles() (in module web2vec.extractors.html_body_features) (in module web2vec.extractors.http_response_features) number_of_parameters (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) number_of_subdomains (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) numeric_chars_ratio() (in module web2vec.extractors.url_lexical_features)

O

online (web2vec.extractors.external_api.phish_tank_features.PhishTankFeatures attribute) open_page_rank_api_key (web2vec.config.Config attribute) OpenPageRankAPI (class in web2vec.extractors.external_api.open_pagerank_features) OpenPageRankExtractor (class in web2vec.crawlers.extractors)

OpenPageRankFeatures (class in web2vec.extractors.external_api.open_pagerank_features) OpenPhishExtractor (class in web2vec.crawlers.extractors) OpenPhishFeatures (class in web2vec.extractors.external_api.open_phish_features) org (web2vec.extractors.whois_features.WhoisFeatures attribute)

P

page_rank_decimal (web2vec.extractors.external_api.open_pagerank_features.OpenPageRankFeatures attribute) PagePerVisit (web2vec.extractors.external_api.similar_web_features.Engagements attribute) PaidReferrals (web2vec.extractors.external_api.similar_web_features.TrafficSource attribute) parameters_length (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) parse() (web2vec.crawlers.spiders.Web2VecSpider method) percentage_numeric_chars (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute)

phish_detail_url (web2vec.extractors.external_api.phish_tank_features.PhishTankFeatures attribute) phish_id (web2vec.extractors.external_api.phish_tank_features.PhishTankFeatures attribute) PhishTankExtractor (class in web2vec.crawlers.extractors) PhishTankFeatures (class in web2vec.extractors.external_api.phish_tank_features) position (web2vec.extractors.external_api.google_index_features.GoogleIndexFeatures attribute) process_extractors() (in module web2vec.crawlers.extractors)

Q

qty_ip_resolved (web2vec.extractors.dns_features.DNSFeatures attribute)

qty_mx_servers (web2vec.extractors.dns_features.DNSFeatures attribute) qty_nameservers (web2vec.extractors.dns_features.DNSFeatures attribute)

R

raw (web2vec.extractors.whois_features.WhoisFeatures attribute) RawData (web2vec.extractors.external_api.similar_web_features.SimilarWebFeatures attribute) record_type (web2vec.extractors.dns_features.DNSRecordFeatures attribute) records (web2vec.extractors.dns_features.DNSFeatures attribute) redirect_count (web2vec.extractors.http_response_features.HttpResponseFeatures attribute) redirects (web2vec.extractors.http_response_features.HttpResponseFeatures attribute) referral_url (web2vec.extractors.whois_features.WhoisFeatures attribute) Referrals (web2vec.extractors.external_api.similar_web_features.TrafficSource attribute)

registrar (web2vec.extractors.whois_features.WhoisFeatures attribute) remote_url_output_path (web2vec.config.Config attribute) repeated_digits_directory (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) repeated_digits_domain (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) repeated_digits_parameters (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) repeated_digits_url (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) reporter (web2vec.extractors.external_api.url_haus_features.URLHausFeatures attribute) right_click_disabled (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) right_click_disabled() (in module web2vec.extractors.html_body_features)

S

sanitize_filename() (in module web2vec.utils) script_length (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) (web2vec.extractors.http_response_features.HttpResponseFeatures attribute) script_length() (in module web2vec.extractors.html_body_features) (in module web2vec.extractors.http_response_features) script_to_body_ratio (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) (web2vec.extractors.http_response_features.HttpResponseFeatures attribute) script_to_body_ratio() (in module web2vec.extractors.html_body_features) (in module web2vec.extractors.http_response_features) script_to_special_chars_ratio (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) (web2vec.extractors.http_response_features.HttpResponseFeatures attribute) script_to_special_chars_ratio() (in module web2vec.extractors.html_body_features) (in module web2vec.extractors.http_response_features) Search (web2vec.extractors.external_api.similar_web_features.TrafficSource attribute) server_client_domain (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) server_version (web2vec.extractors.http_response_features.HttpResponseFeatures attribute) set_correct_path() (web2vec.config.Config class method)

SimilarWebExtractor (class in web2vec.crawlers.extractors) SimilarWebFeatures (class in web2vec.extractors.external_api.similar_web_features) SiteName (web2vec.extractors.external_api.similar_web_features.SimilarWebFeatures attribute) Social (web2vec.extractors.external_api.similar_web_features.TrafficSource attribute) source_mode (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) special_characters (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) (web2vec.extractors.http_response_features.HttpResponseFeatures attribute) special_characters() (in module web2vec.extractors.html_body_features) (in module web2vec.extractors.http_response_features) ssl_verify (web2vec.config.Config attribute) state (web2vec.extractors.whois_features.WhoisFeatures attribute) status (web2vec.extractors.whois_features.WhoisFeatures attribute) store_json() (in module web2vec.utils) subdomain_count (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) subject (web2vec.extractors.ssl_certification_features.CertificateFeatures attribute) submission_time (web2vec.extractors.external_api.phish_tank_features.PhishTankFeatures attribute) suspicious_file_extension (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute)

T

tags (web2vec.extractors.external_api.url_haus_features.URLHausFeatures attribute) target (web2vec.extractors.external_api.phish_tank_features.PhishTankFeatures attribute) threat (web2vec.extractors.external_api.url_haus_features.URLHausFeatures attribute) time_domain_activation (web2vec.extractors.whois_features.WhoisFeatures attribute) time_domain_expiration (web2vec.extractors.whois_features.WhoisFeatures attribute) time_response (web2vec.extractors.http_response_features.HttpResponseFeatures attribute) TimeOnSite (web2vec.extractors.external_api.similar_web_features.Engagements attribute) Title (web2vec.extractors.external_api.similar_web_features.SimilarWebFeatures attribute) tld_amount_url (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) tld_count() (in module web2vec.extractors.url_lexical_features) tld_popularity (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) tld_presence_in_arguments (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) token_count (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute)

token_count() (in module web2vec.extractors.url_lexical_features) TopCountryShare (class in web2vec.extractors.external_api.similar_web_features) TopCountryShares (web2vec.extractors.external_api.similar_web_features.SimilarWebFeatures attribute) TopKeyword (class in web2vec.extractors.external_api.similar_web_features) TopKeywords (web2vec.extractors.external_api.similar_web_features.SimilarWebFeatures attribute) TrafficSource (class in web2vec.extractors.external_api.similar_web_features) TrafficSources (web2vec.extractors.external_api.similar_web_features.SimilarWebFeatures attribute) transform_value() (in module web2vec.utils) trust_message (web2vec.extractors.ssl_certification_features.CertificateFeatures attribute) ttl (web2vec.extractors.dns_features.DNSRecordFeatures attribute) ttl_expires_within_day (web2vec.extractors.dns_features.DNSFeatures attribute) ttl_expires_within_hour (web2vec.extractors.dns_features.DNSFeatures attribute) ttl_expires_within_week (web2vec.extractors.dns_features.DNSFeatures attribute) ttl_hostname (web2vec.extractors.dns_features.DNSFeatures attribute)

U

updated_date (web2vec.extractors.external_api.open_pagerank_features.OpenPageRankFeatures attribute) (web2vec.extractors.whois_features.WhoisFeatures attribute) url (web2vec.extractors.external_api.phish_tank_features.PhishTankFeatures attribute) (web2vec.extractors.external_api.url_haus_features.URLHausFeatures attribute) (web2vec.extractors.url_geo_features.URLGeoFeatures attribute) url_depth (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) url_depth() (in module web2vec.extractors.url_lexical_features) url_google_index (web2vec.extractors.external_api.google_index_features.GoogleIndexFeatures attribute) url_length (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) url_shortened (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute)

url_status (web2vec.extractors.external_api.url_haus_features.URLHausFeatures attribute) UrlGeoExtractor (class in web2vec.crawlers.extractors) URLGeoFeatures (class in web2vec.extractors.url_geo_features) urlhaus_link (web2vec.extractors.external_api.url_haus_features.URLHausFeatures attribute) UrlHausExtractor (class in web2vec.crawlers.extractors) URLHausFeatures (class in web2vec.extractors.external_api.url_haus_features) UrlLexicalExtractor (class in web2vec.crawlers.extractors) URLLexicalFeatures (class in web2vec.extractors.url_lexical_features) uses_https (web2vec.extractors.http_response_features.HttpResponseFeatures attribute) uses_shortening_service (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute) uses_shortening_service() (in module web2vec.extractors.url_lexical_features)

V

valid_in_30_days (web2vec.extractors.ssl_certification_features.CertificateFeatures attribute) valid_in_7_days (web2vec.extractors.ssl_certification_features.CertificateFeatures attribute) valid_ip() (in module web2vec.utils) validity_duration_days (web2vec.extractors.ssl_certification_features.CertificateFeatures attribute) validity_message (web2vec.extractors.ssl_certification_features.CertificateFeatures attribute) Value (web2vec.extractors.external_api.similar_web_features.TopCountryShare attribute) values (web2vec.extractors.dns_features.DNSRecordFeatures attribute)

verification_time (web2vec.extractors.external_api.phish_tank_features.PhishTankFeatures attribute) verified (web2vec.extractors.external_api.phish_tank_features.PhishTankFeatures attribute) Version (web2vec.extractors.external_api.similar_web_features.SimilarWebFeatures attribute) Visits (web2vec.extractors.external_api.similar_web_features.Engagements attribute) visits (web2vec.extractors.external_api.similar_web_features.EstimatedMonthlyVisit attribute) Volume (web2vec.extractors.external_api.similar_web_features.TopKeyword attribute) vowel_count_domain (web2vec.extractors.url_lexical_features.URLLexicalFeatures attribute)

W

was_js_rendered (web2vec.extractors.html_body_features.HtmlBodyFeatures attribute) web2vec module web2vec.config module web2vec.crawlers module web2vec.crawlers.extractors module web2vec.crawlers.models module web2vec.crawlers.spiders module web2vec.extractors module web2vec.extractors.dns_features module web2vec.extractors.external_api module web2vec.extractors.external_api.google_index_features module web2vec.extractors.external_api.open_pagerank_features module web2vec.extractors.external_api.open_phish_features module web2vec.extractors.external_api.phish_tank_features module

web2vec.extractors.external_api.similar_web_features module web2vec.extractors.external_api.url_haus_features module web2vec.extractors.html_body_features module web2vec.extractors.http_response_features module web2vec.extractors.network_features module web2vec.extractors.ssl_certification_features module web2vec.extractors.url_geo_features module web2vec.extractors.url_lexical_features module web2vec.extractors.whois_features module web2vec.utils module web2vec.version module Web2VecSpider (class in web2vec.crawlers.spiders) WebPage (class in web2vec.crawlers.models) whois_server (web2vec.extractors.whois_features.WhoisFeatures attribute) WhoisExtractor (class in web2vec.crawlers.extractors) WhoisFeatures (class in web2vec.extractors.whois_features)

Y

Year (web2vec.extractors.external_api.similar_web_features.Engagements attribute)

Z

zipcode (web2vec.extractors.whois_features.WhoisFeatures attribute)